quantize: filter per-layer metadata when pruning layers (#27976) - #28597
Open
Sumire-no-kai wants to merge 1 commit into
Open
quantize: filter per-layer metadata when pruning layers (#27976)#28597Sumire-no-kai wants to merge 1 commit into
Sumire-no-kai wants to merge 1 commit into
Conversation
Pruning model layers updates block\_count and tensor lists, but leaves per-layer GGUF metadata arrays at their original length. This mismatch causes load failures or metadata inconsistency for pruned models. Filter known per-layer metadata arrays by original layer index during layer pruning while preserving their original GGUF data types. Add regression tests covering metadata array truncation, removal of deleted layer elements, preservation of scalar and non-layer metadata, and reloading of the pruned model.
Sumire-no-kai
requested review from
JohannesGaessler and
ggerganov
as code owners
September 8, 2026 09:13
This comment was marked as resolved.
This comment was marked as resolved.
github-actions
Bot
removed
the
draft
Sumire-no-kai
marked this pull request as ready for review
September 8, 2026 09:28
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Pruning model layers updates block_count and tensor lists, but leaves per-layer GGUF metadata arrays at their original length. This mismatch causes load failures or metadata inconsistency for pruned models.
Filter known per-layer metadata arrays by original layer index during layer pruning while preserving their original GGUF data types.
Add regression tests covering metadata array truncation, removal of deleted layer elements, preservation of scalar and non-layer metadata, and reloading of the pruned model.
Fixes #27976
Requirements